PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge Transfer
This addresses the bottleneck of persona availability and privacy in dialogue systems, offering a parameter-efficient solution for creating personalized agents, though it is incremental as it builds on existing pre-trained language models.
The paper tackles the problem of building personalized dialogue agents without explicit persona descriptions, which can be unavailable or pose privacy concerns, by introducing PersonaPKT, a lightweight transfer learning approach that adds less than 0.1% trainable parameters per persona and outperforms baselines in persona consistency while maintaining response quality.
Personalized dialogue agents (DAs) powered by large pre-trained language models (PLMs) often rely on explicit persona descriptions to maintain personality consistency. However, such descriptions may not always be available or may pose privacy concerns. To tackle this bottleneck, we introduce PersonaPKT, a lightweight transfer learning approach that can build persona-consistent dialogue models without explicit persona descriptions. By representing each persona as a continuous vector, PersonaPKT learns implicit persona-specific features directly from a small number of dialogue samples produced by the same persona, adding less than 0.1% trainable parameters for each persona on top of the PLM backbone. Empirical results demonstrate that PersonaPKT effectively builds personalized DAs with high storage efficiency, outperforming various baselines in terms of persona consistency while maintaining good response generation quality. In addition, it enhances privacy protection by avoiding explicit persona descriptions. Overall, PersonaPKT is an effective solution for creating personalized DAs that respect user privacy.